# Community Concealment from Graph Neural Networks

arXiv: https://arxiv.org/abs/2602.12250 · HTML: https://mlsanity.com/paper/2602.12250/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 79 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Builds on (most cited first, 30 of 37)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Hierarchical Graph Representation Learning with Differentiable Pooling](https://mlsanity.com/paper/1806.08804/) (2018)
- [Self-Normalizing Neural Networks](https://mlsanity.com/paper/1706.02515/) (2017)
- [Adversarial Attacks on Neural Networks for Graph Data](https://mlsanity.com/paper/1805.07984/) (2018)
- [From Louvain to Leiden: guaranteeing well-connected communities](https://mlsanity.com/paper/1810.08473/) (2018)
- [Adversarial Attacks on Graph Neural Networks via Meta Learning](https://mlsanity.com/paper/1902.08412/) (2019)
- [Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics](https://mlsanity.com/paper/1908.02591/) (2019)
- [Graph Clustering with Graph Neural Networks](https://mlsanity.com/paper/2006.16904/) (2020)
- [Graph Backdoor](https://mlsanity.com/paper/2006.11890/) (2020)
- [Towards Explainable Artificial Intelligence](https://mlsanity.com/paper/1909.12072/) (2019)
- [Unsupervised Attributed Multiplex Network Embedding](https://mlsanity.com/paper/1911.06750/) (2019)
- [Hiding Individuals and Communities in a Social Network](https://mlsanity.com/paper/1608.00375/) (2016)
- [Fast Gradient Attack on Network Embedding](https://mlsanity.com/paper/1809.02797/) (2018)
- [LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis](https://mlsanity.com/paper/2108.06504/) (2021)
- [Understanding Random Forests: From Theory to Practice](https://mlsanity.com/paper/1407.7502/) (2014)
- [Uncovering Coordinated Networks on Social Media: Methods and Case Studies](https://mlsanity.com/paper/2001.05658/) (2020)
- [The ground truth about metadata and community detection in networks](https://mlsanity.com/paper/1608.05878/) (2016)
- [A Comparative Analysis of Community Detection Algorithms on Artificial Networks](https://mlsanity.com/paper/1608.00763/) (2016)
- [PANE: scalable and effective attributed network embedding](https://mlsanity.com/paper/2009.00826/) (2020)
- [Adversarial Attack on Community Detection by Hiding Individuals](https://mlsanity.com/paper/2001.07933/) (2020)
- [Element-centric clustering comparison unifies overlaps and hierarchy](https://mlsanity.com/paper/1706.06136/) (2017)
- [Synthetic Graph Generation to Benchmark Graph Learning](https://mlsanity.com/paper/2204.01376/) (2022)
- [Community detection in networks: Structural communities versus ground truth](https://mlsanity.com/paper/1406.0146/) (2014)
- [GA Based Q-Attack on Community Detection](https://mlsanity.com/paper/1811.00430/) (2018)
- [Multiscale Evolutionary Perturbation Attack on Community Detection](https://mlsanity.com/paper/1910.09741/) (2019)

## Abstract (arXiv)

Graph neural networks (GNNs) enable powerful unsupervised learning of communities. However, such inference may inadvertently expose sensitive group structures, critical clustered patterns, or collective behaviors, raising concerns about sensitive group-level privacy. In social and critical infrastructure networks, unauthorized community inference can reveal coordinated asset groups, operational hierarchies, and system dependencies that may be exploited for reconnaissance or profiling. We study a defensive setting in which a network (or defender) operator seeks to conceal a community of interest while making only small, utility-preserving modifications to the network. Our analysis shows that community concealment depends on two measurable factors: the connectivity at the community boundary and the feature similarity between the protected community and its neighbors. Guided by these observations, we introduce Feature-Community-guided DICE (FCom-DICE), a perturbation strategy built on DICE (Disconnect Internally Connect Externally) that rewires a set of structurally influential edges and adjusts node features to reduce the distinctiveness exploited by GNN message passing. Across synthetic benchmarks and real network graphs such as Facebook, Wikipedia, and Bitcoin Transactions, FCom-DICE consistently outperforms structure-only DICE under the same perturbation budgets. The largest improvements are observed for communities that are weakly connected to the rest of the network and well separated in feature space. These gains are achieved while preserving key structural and feature characteristics of the original network. These results demonstrate the effectiveness of feature-aware perturbations for reducing the recoverability of targeted communities under GNN-based community inference.